AUTHOR=Wang Shuwang , Liu Feng , Yin Xin-xin , Chen Kerui , Cai Run 

TITLE=Employing convolution-enhanced attention mechanisms for earthquake detection and phase picking models

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1283857

DOI=10.3389/feart.2023.1283857

ISSN=2296-6463

ABSTRACT=Addressing the issue of poor performance in low signal-to-noise ratio event detection for earthquake detection deep learning models, this article presents a novel earthquake detection model-ECPickNet. Inspired by the EQTransformer, the model employs the convolution-enhanced Transformer technology, Conformer, and integrates the Residual Stacking Block Unit with Channel-Skipping(RSBU-CS) module. The manuscript elaborates on the model's network architecture, parameter settings during the training process, and compares it with multiple similar methods through experiments. Experimental results demonstrate that the ECPickNet outperforms other methods on both the STEAD and Gansu datasets, particularly exhibiting powerful performance in processing low signal-to-noise ratio data. The method we propose can be accessed and downloaded through the following website ad-dress: https://github.com/20041170036/EcPick.